def get_embeds(g):
d = {}
for n in g.nodes:
d[n] = str(n)
g1 = nx.relabel_nodes(g, d)
graph_model = DeepWalk(g1, num_walks=args.num_walks, walk_length=args.walk_len,
workers=args.cpu if args.cpu > 0 else cpu_count())
graph_model.train(window_size=args.win, iter=args.emb_iters, embed_size=action_dim)
embs = {}
emb1 = graph_model.get_embeddings()
for n in emb1.keys():
embs[int(n)] = emb1[n]
return embs
X, Y = read_node_label('../data/wiki_labels.txt')
emb_list = []
for k in X:
emb_list.append(embeddings[k])
emb_list = np.array(emb_list)
model = TSNE(n_components=2)
node_pos = model.fit_transform(emb_list)
color_idx = {}
for i in range(len(X)):
color_idx.setdefault(Y[i][0], [])
color_idx[Y[i][0]].append(i)
for c, idx in color_idx.items():
plt.scatter(node_pos[idx, 0], node_pos[idx, 1], label=c)
plt.legend()
plt.show()
if __name__ == '__main__':
G = nx.read_edgelist('../data/Wiki_edgelist.txt',
create_using=nx.DiGraph(), nodetype=None, data=[("weight", int)])
print(len(G.nodes()))
model = DeepWalk(G, walk_length=10, num_walks=80, workers=1)
model.train(w_size=5, iter_num=3)
embeddings = model.get_embedding_all()
evaluate_embeddings(embeddings)
plot_embeddings(embeddings)
from deepwalk import DeepWalk
random.seed(616)
edges = np.load('../tencent/train_edges.npy')
G = nx.Graph()
for i in range(169209):
G.add_node(i)
G.add_edges_from(edges)
deepwalk = DeepWalk(G,
emb_size=128,
length_walk=50,
num_walks=10,
window_size=10,
num_iters=2)
w2v = deepwalk.train(workers=4, is_loadmodel=False, is_loaddata=False)
pos_test = np.load('../tencent/test_edges.npy')
neg_test = np.load('../tencent/test_edges_false.npy')
y_true = [True] * pos_test.shape[0] + [False] * neg_test.shape[0]
X = np.vstack([pos_test, neg_test])
print('Testing...')
y_score = []
for u, v in X:
y_score.append(w2v.wv.similarity(str(u), str(v)))
auc_test = roc_auc_score(y_true, y_score)
print('Tencent, test AUC:', auc_test)
Author : haxu
dateļ¼ 2019/4/3
-------------------------------------------------
Change Activity:
2019/4/3:
-------------------------------------------------
"""
__author__ = 'haxu'
import networkx as nx
from deepwalk import DeepWalk
from classify import read_node_label, Classifier
from sklearn.linear_model import LogisticRegression
if __name__ == '__main__':
G = nx.read_edgelist('../data/Wiki_edgelist.txt',
create_using=nx.DiGraph(),
nodetype=None,
data=[('weight', int)])
model = DeepWalk(G, walk_length=30, num_walks=80, workers=4)
model.train(window_size=5, iter=3)
embeddings = model.get_embeddings()
X, Y = read_node_label('../data/wiki_labels.txt')
tr_frac = 0.8
clf = Classifier(embeddings=embeddings, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, tr_frac)